A5073450425- Social Robot Interaction and HRI
- Robotics and Automated Systems
- Context-Aware Activity Recognition Systems
- Robot Manipulation and Learning
- Teleoperation and Haptic Systems
- Reinforcement Learning in Robotics
- Gaze Tracking and Assistive Technology
- Speech and Audio Processing
- Indoor and Outdoor Localization Technologies
- Robotic Locomotion and Control
- Robotic Path Planning Algorithms
- Tactile and Sensory Interactions
- Industrial Vision Systems and Defect Detection
- Technology Use by Older Adults
- Robotics and Sensor-Based Localization
- Manufacturing Process and Optimization
- Advancements in Photolithography Techniques
- Music and Audio Processing
- Prosthetics and Rehabilitation Robotics
- Advanced Vision and Imaging
- IoT and Edge/Fog Computing
- Control and Dynamics of Mobile Robots
- Advanced Manufacturing and Logistics Optimization
- Psychiatry, Mental Health, Neuroscience
- Energy Efficient Wireless Sensor Networks
Université de Sherbrooke
2013-2024
Laboratoire d’Informatique et Systèmes
2019
École Nationale Supérieure de Techniques Avancées
2014-2018
Université Paris-Saclay
2016-2017
Abstract Recent technological advances enabled modern robots to become part of our daily life. In particular, assistive robotics emerged as an exciting research topic that can provide solutions improve the quality life elderly and vulnerable people. This paper introduces robotic platform developed in ENRICHME project, with particular focus on its innovative perception interaction capabilities. The project’s main goal is enrich day-to-day experience people at home technologies enable health...
ManyEars is an open framework for microphone array-based audio processing. It consists of a sound source localization, tracking and separation system that can provide enhanced speaker signal improved speech recognition in real-world settings. software composed portable modular C library, along with graphical user interface tuning the parameters real-time monitoring. This paper presents integration Library Willow Garage's Robot Operating System. To facilitate use on various robotic platforms,...
The user interface is the central element of a telepresence robotic system and its visualization modalities greatly affect operator's situation awareness, thus performance. Depending on task at hand preferences, going from ego- exocentric viewpoints improving depth representation can provide better perspectives operation environment. Our system, which combines 3D reconstruction environment using laser range finder readings with two video projection methods, allows operator to easily switch...
One typical remote consultation envisioned for in-home telerehabilitation involves having the patient exercise on a stationary bike. Making sure that is breathing well while pedaling of primary concern clinician. key requirement to make system as simple possible patients, avoiding, instance, have them wear sensors and devices. This paper presents contact-free respiration rate monitoring measuring temperature variations between inspired expired air in mouth-nose region using thermal imaging....
Designing robots that interact naturally with people requires the integration of technologies and algorithms for communication modalities such as gestures, movement, facial expressions user interfaces. To understand interdependence among these modalities, evaluating integrated design in feasibility studies provides insights about key considerations regarding robot potential interaction scenarios, allowing to be iteratively refined before larger-scale experiments are planned conducted. This...
Head pose assessment can reveal important clinical information on human motor control. Quantitative have the potential to objectively evaluate head and movements' specifics, in order monitor progression of a disease or effectiveness treatment. Optoelectronic camera-based motion-capture systems, recognized as gold standard biomechanics, been proposed for estimation. However, these systems require markers be positioned person's face which is impractical everyday practice. Furthermore, limited...
For companion robots to properly interact with people, they should be able gain awareness of their effect on the person's state and learn behave accordingly. Advances in physiological monitoring sensors, such as infrared cameras, may enable get an insight a emotional state, which has strong correlation parameters. Performing this contact-free, user transparent manner is important requirement. In paper, we used thermal imaging sensor mounted Meka humanoid robot, remotely measure temperature...
A microphone array can provide a mobile robot with the capability of localizing, tracking and separating distant sound sources in 2D, i.e., estimating their relative elevation azimuth. To combine acoustic data visual information real world settings, spatial correlation must be established. The approach explored this paper consists having two robots, each equipped array, localizing themselves shared reference map using SLAM. Based on locations, from arrays are used to triangulate 3D location...
Commercial telepresence robots provide video, audio, and proximity data to remote operators through a teleoperation user interface running on standard computing devices. As new modalities such as force sensing sound localization are being developed tested advanced robotic platforms, ways integrate information required. This paper demonstrates the use of visual representations forces in 3D interface. Forces represented using colors, size, bar graphs arrows, while speech or ring bubbles used...
Guiding a mobile robot by the hand would make simple and natural interface. This requires ability to sense forces applied on from direct physical contacts, translate these into motion commands. paper presents joint-space impedance control approach that does so perceiving compliant arms, making react as real-life object user pulling pushing one or both of its arms. By independently controlling stiffness in specific degrees-of-freedom, our allows general position arms change preferences person...
Abstract The field of robotics has made steady progress in the pursuit bringing autonomous machines into real-life settings. Over last 3 years, we have seen omnidirectional humanoid platforms that now bring compliance, robustness and adaptiveness to handle unconstrained situations real world. However, today’s contributions mostly address only a portion physical, cognitive or evaluative dimensions, which are all interdependent. This paper presents an overview our attempt integrate as whole...
A common goal of robot control architecture designers is to create systems that are sufficiently generic be adapted different hardware. Beyond code re-use from a software engineering standpoint, having could lead long-term experiments spanning multiple robots and research groups. This paper presents first step toward this with HBBA, Hybrid Behavior-Based Architecture developed on the IRL-1 humanoid integrating an Adaptive Resonance Theory-based episodic memory (EM-ART). adaptation two...
Modern autonomous robots must integrate multiple perceptual and behavioral modalities to be useful in our daily lives. Such integration is constrained by the limited onboard computing capacity of robotic platforms. To alleviate this issue, filtering, a selective attention mechanism, can used efficiently manage resources based on what robot has accomplish. This paper describes implementation filtering control architecture, implemented using operating system (ROS), how it dynamically optimize...
Abstract In health care, a telepresence robot could be used to have clinician or caregiver assist seniors in their homes, without having travel these locations. However, the usability of platforms for such applications requires that they can navigate and interact with certain level autonomy. For instance, robots should able go charging station case low energy telecommunication failure. The remote operator assisted by robot’s capabilities safely at home follow track people whom interact. This...